• Publications
  • Influence
ComboGAN: Unrestrained Scalability for Image Domain Translation
The past year alone has seen unprecedented leaps in the area of learning-based image translation, namely Cycle-GAN, by Zhu et al. But experiments so far have been tailored to merely two domains at aExpand
  • 81
  • 15
  • Open Access
Night-to-Day Image Translation for Retrieval-based Localization
Visual localization is a key step in many robotics pipelines, allowing the robot to (approximately) determine its position and orientation in the world. An efficient and scalable approach to visualExpand
  • 50
  • 5
  • Open Access
Efficient floating point precision tuning for approximate computing
This paper presents an automatic tool-chain that efficiently computes the precision of floating point variables down to the bit level of the mantissa. Our toolchain uses a distributed algorithm thatExpand
  • 27
  • 1
  • Open Access
Symmetry in the Eye of the Beholder
We study how subjective perception of symmetry can be computationally explained by features at different levels. We select 149 images with varying degrees of symmetry from photographs and movieExpand
  • 1
  • Open Access
Conditional Neural Style Transfer with Peer-Regularized Feature Transform
This paper introduces a neural style transfer model to conditionally generate a stylized image using only a set of examples describing the desired style. The proposed solution produces high-qualityExpand
Image Transformation via Neural Network Inversion
While prior experiments have shown it is possible to approximately reconstruct inputs to a neural net given an output from one of its frontal layers, it becomes increasingly difficult as one movesExpand
Two-Stage Peer-Regularized Feature Recombination for Arbitrary Image Style Transfer
This paper introduces a neural style transfer model to generate a stylized image conditioning on a set of examples describing the desired style. The proposed solution produces high-quality imagesExpand
Novel Identification and Grouping of Growing Astronomical Supernovae
For years, researchers have been manually classifying images, searching for new supernovae. We propose a system for automatically detecting supernovae. Our multi-step pipeline takes in two images, aExpand
Real-time Classification from Short Event-Camera Streams using Input-filtering Neural ODEs
Event-based cameras are novel, efficient sensors inspired by the human vision system, generating an asynchronous, pixel-wise stream of data. Learning from such data is generally performed throughExpand